{"id":"W3007557661","doi":"10.1109/icra40945.2020.9197562","title":"Self-Supervised Deep Pose Corrections for Robust Visual Odometry","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Visual odometry; Artificial intelligence; Odometry; Computer science; Ground truth; Estimator; Pose; Monocular; Computer vision; Supervised learning; Pattern recognition (psychology); Machine learning; Mathematics; Robot; Artificial neural network; Mobile robot","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00006478935,0.0002918674,0.0003263543,0.0001768301,0.00008023311,0.0001170763,0.0001632867,0.0003497968,0.0001527564],"category_scores_gemma":[0.00006054311,0.0003149028,0.0001956778,0.0002413964,0.00001070061,0.00004191827,0.00009532897,0.0003534492,0.00005023364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001318232,"about_ca_system_score_gemma":0.00004351578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001960225,"about_ca_topic_score_gemma":0.00002751989,"domain_scores_codex":[0.9989113,0.0000192301,0.0003286525,0.0003435713,0.0001509501,0.0002463271],"domain_scores_gemma":[0.9993528,0.00009755397,0.00003527863,0.0002460192,0.0001214029,0.0001470095],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007524062,0.00004587267,0.00006369228,0.0005534794,0.0001382819,0.000002104134,0.0001301412,0.9934966,0.0001713295,0.0004029268,0.003201087,0.001786982],"study_design_scores_gemma":[0.0003146573,0.00004621273,0.00004722982,0.00002562801,0.0000975611,0.000001230945,0.00008942313,0.9963992,0.0005807413,0.0001929384,0.001839769,0.0003654144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002115915,0.0001407968,0.9883077,0.0001446407,0.003010562,0.0006848502,0.00003654841,0.001500291,0.004058693],"genre_scores_gemma":[0.5180895,0.000400395,0.4765276,0.0004525657,0.001755468,0.0002274426,0.001679779,0.0003662783,0.0005009513],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5159736,"threshold_uncertainty_score":0.9999303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02530821469046263,"score_gpt":0.2421166221894535,"score_spread":0.2168084074989909,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}